Zum Inhalt springen

Beschreibungen der Umgebungsvariablen (Rohangabe)

7.577 verschiedene Werte, gemessen an 42.703 ausgelieferten Einträgen.

Wert Einträge Anteil
ANDISH_API_KEY=Andish API key. Create one in the dashboard at https://andish.ru · ANDISH_BASE_URL=API base URL. Defaults to the hosted service; set it only when pointing at your own deployment. 1 0.0 %
ANDREANI_API_KEY=API key for Andreani · ANDREANI_PASSWORD=Password for Andreani · ANDREANI_USER=Username for Andreani 1 0.0 %
ANDROIDAPI_SECRET=Your API key from AndroidAPI.net → Tools → API Keys 1 0.0 %
ANDROID_HOME=Path to Android SDK (auto-detected on macOS at ~/Library/Android/sdk) 1 0.0 %
ANDRU_API_KEY=Your Andru Platform API key. Get one at https://platform.andru-ai.com/settings/developer · ANDRU_API_URL=Andru API base URL (default: https://api.andru-ai.com) 1 0.0 %
ANGEL_API_KEY=Angel One SmartAPI app key · ANGEL_CLIENT_ID=Angel One client code · ANGEL_PASSWORD=Angel One password or MPIN · ANGEL_TOTP_SECRET=Base32 TOTP secret used to generate login OTPs · HARD_MAX_ORDER_QTY=Hard max order quantity · HARD_MAX_ORDER_VALUE=Hard max order value in INR · SOFT_MAX_ORDER_QTY=Soft max order quantity · SOFT_MAX_ORDER_VALUE=Soft max order value in INR 1 0.0 %
ANGI_DEBUG=Set to 1 for verbose bridge logging to stderr. · ANGI_WS_PORT=Override the fetchproxy WebSocket port (default 37149). · FETCHPROXY_IDENTITY_DIR=Absolute path where fetchproxy stores its long-term identity keypair (default ~/.fetchproxy/identity/). For a host that runs a separate child per caller, so they share one identity. · FETCHPROXY_WS_HOST=Bind interface for the fetchproxy concentrator (default 127.0.0.1; a literal IP only). For a hosted child in its own network namespace only — never bind a laptop's concentrator to the network. 1 0.0 %
ANILIST_ACCESS_TOKEN=Optional. A pre-obtained AniList access token, as an alternative to running login_anilist. · ANILIST_CLIENT_ID=Optional. From an app registered at anilist.co/settings/developer — needed to use login_anilist. · ANILIST_CLIENT_SECRET=Optional. Paired with the Client ID above — needed to use login_anilist. · ANILIST_OAUTH_PORT=Optional. Localhost port for the login_anilist callback (default 8082). · ANILIST_TOKEN_STORE=Optional. Overrides where the AniList access token is persisted (defaults under the OS config dir). 1 0.0 %
ANILIST_TOKEN=AniList API token for authenticated requests 1 0.0 %
ANIMALHOUSE_API_KEY=API key from animalhouse.ai (ah_ prefix). Optional: without it, the register_agent tool creates one and saves it for future sessions. · ANIMALHOUSE_KEY_FILE=Optional. Where to save and read the key. Default: ~/.config/animalhouse/credentials.json. 1 0.0 %
ANIMICA_API_KEY=Optional Animica API key (anm_live_...) for higher AI rate limits. The server works without it. · ANIMICA_BASE_URL=OpenAI-compatible /v1 base URL used for AI inference (chat + models). https://animica.dev/v1 is the free keyless endpoint. · ANIMICA_BEACON_URL=Quantum randomness beacon base URL (/beacon/* endpoints). · ANIMICA_MCP_TIMEOUT_S=HTTP timeout in seconds for backend calls. · ANIMICA_MODEL=Default model id for the animica_ai_ask tool. · ANIMICA_POOL_URL=Mining-pool stats API base URL. · ANIMICA_RPC_URL=Animica node JSON-RPC endpoint (read-only allow-listed methods only). 1 0.0 %
ANKR_API_KEY=Ankr API key. Create one at ankr.com/rpc. 1 0.0 %
ANKUSDRIVE_FREECADCMD=Absolute path to FreeCAD 1.1's freecadcmd. Leave unset to auto-discover on PATH and standard install locations. 1 0.0 %
ANNAS_ACCOUNT_COOKIE=Optional aa_account_id2 cookie from a signed-in browser, for when signing in with the secret key fails. · ANNAS_DOWNLOAD_PATH=Folder for downloaded files. Defaults to annas-archive in your home folder. · ANNAS_SECRET_KEY=The secret key you log in to Anna's Archive with. The server signs in with it and uses it for downloads. 1 0.0 %
ANNEALBRIDGE_ALLOW_REMOTE=Set to true to allow remote vendor backends; local backends need nothing. 1 0.0 %
ANNOLUX_API_KEY=Annolux API key created in the account dashboard. · ANNOLUX_API_URL=Annolux API origin. 1 0.0 %
ANN_LOG_LEVEL=silent, error, info or debug. Default error. · ANN_MIN_INTERVAL_MS=Minimum milliseconds between requests. Default 1100, floor 1000. · ANN_USER_AGENT=Override the User-Agent sent to Anime News Network. 1 0.0 %
ANOMALY_API_BASE=Optional hosted API base URL override. Defaults to https://anomaly.forgemesh.io. 1 0.0 %
ANONYMIZED_TELEMETRY=Enable anonymized usage telemetry (true/false) · OPENBROWSER_ALLOWED_DOMAINS=Comma-separated list of allowed domains (empty for no restrictions) · OPENBROWSER_COMPACT_DESCRIPTION=Use minimal tool description (~500 tokens instead of ~1,430) · OPENBROWSER_HEADLESS=Run browser in headless mode (true/false) · OPENBROWSER_MAX_OUTPUT=Maximum output characters per code execution (default: 10000) · OPENBROWSER_STORAGE_STATE=Optional JSON file used as a one-time seed for cookies plus localStorage in managed MCP profiles; later updates are saved to the active profile copy · OPENBROWSER_USER_DATA_DIR=Optional explicit Chrome profile directory. Omit for an isolated profile per MCP server instance; concurrent owners of one explicit profile are rejected 1 0.0 %
ANP2_KEY_FILE=Path to the Ed25519 identity file. Defaults to ~/.anp2/key.priv. · ANP2_PRIVATE_KEY=Optional Ed25519 private key as 64-char hex. Overrides ANP2_KEY_FILE. · ANP2_RELAY_PASSWORD=Basic-auth password for the private Phase 0-1 relay. Shared out-of-band. · ANP2_RELAY_URL=Base URL of the ANP2 relay (defaults to https://anp2.com/api). · ANP2_RELAY_USER=Basic-auth user for the private Phase 0-1 relay (use 'relay'). 1 0.0 %
ANP2_KEY_FILE=Path to the Ed25519 identity file. Defaults to ~/.anp2/key.priv. · ANP2_PRIVATE_KEY=Optional Ed25519 private key as 64-char hex. Overrides ANP2_KEY_FILE. · ANP2_RELAY_URL=Base URL of the ANP2 relay (defaults to https://anp2.com/api). 1 0.0 %
ANTEATER_API_KEY=Your own Anteater API key. Optional, but anonymous calls share a global hourly quota. Request one at https://dashboard.anteaterapi.com and choose type 'secret'. · ANTEATER_MCP_TOKEN=Shared secret clients must present as 'Authorization: Bearer <token>'. Required before exposing the server beyond loopback. · ANTEATER_TRUSTED_PROXIES=Which peers may set X-Forwarded-*. Defaults to 'private', which covers the Docker bridge. Without it the server ignores forwarded headers, because they are client-supplied. · ZOTCOURSE_API_BASE=Independent fallback for live schedule data when Anteater API is unavailable. Set to 'off' to disable. 1 0.0 %
ANTFEED_EXPLORER_URL=Base URL for the AntFeed Explorer REST API. · ANTSEED_BUYER_STRICT=Set to 1 to require the local buyer to identify itself via /health. Recommended on shared dev boxes. · ANTSEED_BUYER_URL=Local AntSeed buyer RPC URL. Required only for the transactional `create_session` tool; omit for read-only use. · ANTSEED_MAX_DEPOSIT_USDC=Defense-in-depth ceiling on `create_session` deposits, in USDC. Hard-capped at 10000. 1 0.0 %
ANTHROPIC_API_KEY=AI provider key used ONLY by the pseolint_orchestrate_audit tool (auto-detects ANTHROPIC_API_KEY / OPENAI_API_KEY / etc.). The other three tools run without it. · PSEOLINT_MCP_SAMPLE_CAP=Optional. Max pages sampled per audit (default 50). 1 0.0 %
ANTHROPIC_API_KEY=API key for Anthropic Claude (default LLM provider) · GEMINI_API_KEY=API key for Google Gemini models · GROQ_API_KEY=API key for Groq models · LLM_MODEL=LLM model to use (default: claude-sonnet-4-6). Supports Anthropic, OpenAI, Gemini, Groq, Ollama via LiteLLM. · OPENAI_API_KEY=API key for OpenAI models 1 0.0 %
ANTHROPIC_API_KEY=API key for Anthropic Claude. Required when MEMOGRAPH_PROVIDER=claude or when using the [anthropic] extra. · MEMOGRAPH_MODEL=Optional LLM model name (e.g. 'claude-sonnet-4-6'). Used together with MEMOGRAPH_PROVIDER. · MEMOGRAPH_PROVIDER=Optional LLM provider for query_with_context tool. Only needed if you want AI-generated answers. · MEMOGRAPH_READONLY=Set to 'true' to block destructive MCP tools (delete_memory, update_memory, bulk_create, batch_delete, batch_update). Recommended for shared or untrusted clients. · MEMOGRAPH_VAULT=Path to your MemoGraph vault directory (created if missing). · OLLAMA_HOST=Base URL for a local Ollama server (default http://localhost:11434). Only needed when MEMOGRAPH_PROVIDER=ollama or the [ollama] extra is installed. · OPENAI_API_KEY=API key for OpenAI. Required when using the [openai] extra (embeddings or LLM). 1 0.0 %
ANTHROPIC_API_KEY=API key for AnthropicApiJudge (only used when feature 'anthropic-api' is built in). · CUBA_JUDGE=cuba_juez backend selector: claude_cli | anthropic_api | heuristic | auto (default auto). · CUBA_JUEZ_CLI=Subprocess CLI used by ClaudeCodeJudge (default 'claude'). · CUBA_JUEZ_MODEL=Model name passed to the judge backend (default 'claude-haiku-4-5'). · CUBA_PROJECT_FILTER=Set to 'off' to disable v0.8 project scoping filters (admin/debug only). · CUBA_REM_RELATION_BATCH=Isolated entities the REM cycle scans for relations per run (default 5, 0 disables). · CUBA_RERANKER_PATH=Directory holding the bge-reranker ONNX model; enables cross-encoder reranking (+93% nDCG on GPU). · CUBA_RERANK_FIXED_SHAPE=Pad reranker batches to a constant 512 tokens. Defaults on for GPU builds, off on CPU. · CUBA_SYNC_DIR=Directory used by cuba_sync export/import (default ./.cuba-memorys/). · DATABASE_URL=PostgreSQL connection URL (e.g. postgresql://user:pass@localhost:5432/brain) 1 0.0 %
ANTHROPIC_API_KEY=API key for Claude AI operations (summarization, analysis) · PROJECT_ROOT=Root directory of the project to track 1 0.0 %
ANTHROPIC_API_KEY=API key for Claude extraction backend (omit when using local/Ollama) · GEMINI_API_KEY=API key for Gemini extraction backend (omit when using local/Ollama) · OPENAI_API_KEY=API key for OpenAI extraction backend (omit when using local/Ollama) 1 0.0 %
ANTHROPIC_API_KEY=API key for the reference Anthropic provider · VERACIUM_DB_PATH=Path to the SQLite memory file (default: veracium.db) · VERACIUM_USER=Default user id when a tool call omits user_id 1 0.0 %
ANTHROPIC_API_KEY=API key used to generate questions and grade open answers. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (CRITIC_PROVIDER=anthropic) · CLAUDE_CODE_CLI_PATH=Path to the claude executable (CRITIC_PROVIDER=claude-code) · CODEX_CLI_PATH=Path to the codex executable (CRITIC_PROVIDER=codex-cli) · CRITIC_CLI_TIMEOUT_MS=Local CLI timeout in milliseconds, from 1000 to 600000 · CRITIC_MODEL=Model id override; required for opencode-cli as provider/model · CRITIC_PERSONA=Critic persona: security-first, performance-freak or clean-code-monk · CRITIC_PROVIDER=Critic provider: openai, anthropic, google, minimax, opencode, codex-cli, claude-code, cursor-agent or opencode-cli (a signed-in local CLI is auto-detected if omitted) · CURSOR_AGENT_CLI_PATH=Path to the agent executable (CRITIC_PROVIDER=cursor-agent) · DEBUG=Log parse and read failures to stderr · GOOGLE_GENERATIVE_AI_API_KEY=Google Gemini API key (CRITIC_PROVIDER=google) · MINIMAX_API_KEY=MiniMax API key (CRITIC_PROVIDER=minimax) · OPENAI_API_KEY=OpenAI API key (CRITIC_PROVIDER=openai) · OPENCODE_API_KEY=OpenCode API key (CRITIC_PROVIDER=opencode) · OPENCODE_CLI_PATH=Path to the opencode executable (CRITIC_PROVIDER=opencode-cli) · OPENCODE_PLAN=OpenCode plan: go (subscription) or zen (pay-as-you-go) · VIBE_WORKSPACE_ROOT=Consumer project root (auto-detected from the working directory if omitted) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (alternative) · GEMINI_API_KEY=Google Gemini API key (alternative) · LIQUID_ALLOW_WRITES=Set to 1 to expose the liquid_execute write tool (database insert/update/delete). Off by default — read-only. · OPENAI_API_KEY=OpenAI (or compatible) API key for discovery · OPENAI_BASE_URL=OpenAI-compatible base URL, e.g. local Ollama/vLLM 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (if using Anthropic provider) · OPENAI_API_KEY=OpenAI API key (if using OpenAI provider) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (leave unset to inherit from parent process) · CLAUDE_ALLOWED_TOOLS=Comma-separated list of available tools (e.g. Read,Grep,Glob for read-only) · CLAUDE_APPEND_PROMPT=Additional system prompt appended to the default · CLAUDE_FACTORY_ONLY=Set to true to expose only the factory wizard tool · CLAUDE_MODEL=Model: sonnet, opus, haiku, or full ID · CLAUDE_PERMISSION_MODE=Permission mode: default, acceptEdits, bypassPermissions, plan · CLAUDE_TOOL_NAME=Tool name prefix (default: claude_code) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (optional — alternative LLM provider) · COHERE_API_KEY=Cohere API key — required for RAG embeddings and reranking · GOOGLE_API_KEY=Google Gemini API key (recommended free-tier LLM provider) · LANGSMITH_API_KEY=LangSmith API key (optional — tracing and observability) · OPENAI_API_KEY=OpenAI API key (optional — alternative LLM provider) · TAVILY_API_KEY=Tavily API key — required for web search and URL extraction 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (optional — required only when using provider=claude) · OPENAI_API_KEY=OpenAI API key (optional — required only when using provider=openai) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (required for the 'ask' tool) · GA4_CREDENTIALS_JSON=Google Analytics 4 service account credentials (inline JSON) · GA4_PROPERTY_ID=Google Analytics 4 property ID · MIXPANEL_PROJECT_ID=Mixpanel project ID · MIXPANEL_SERVICE_ACCOUNT_SECRET=Mixpanel service account secret · MIXPANEL_SERVICE_ACCOUNT_USERNAME=Mixpanel service account username · POSTHOG_API_KEY=PostHog personal API key · POSTHOG_PROJECT_ID=PostHog project ID 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (required if using the default Anthropic model) · OPENAI_API_KEY=OpenAI API key (required when TEXT2SQL_MODEL is set to an openai:* model) · TEXT2SQL_DATABASE_URL=SQLAlchemy connection URL, e.g. sqlite:///mydb.db or postgresql://user:pass@host/db · TEXT2SQL_MODEL=Optional LangChain model id (default: anthropic:claude-sonnet-4-6) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (required when using the default Anthropic provider) · LLM_MODEL=Model name override (e.g. claude-sonnet-4-6, gpt-4o) · LLM_PROVIDER=LLM provider: anthropic (default), openai, or ollama · OPENAI_API_KEY=OpenAI API key (required when using LLM_PROVIDER=openai) · SEMANTIC_SCHOLAR_API_KEY=Semantic Scholar API key for higher rate limits on citation lookup (optional) · UNPAYWALL_EMAIL=Email address for Unpaywall API access to improve PDF retrieval (optional) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (use this OR OPENAI_API_KEY OR OLLAMA_HOST) · GSEP_PRESET=Intelligence preset: minimal, standard, conscious, or full (default: full) · OLLAMA_HOST=Ollama server URL for local models (e.g. http://localhost:11434) · OPENAI_API_KEY=OpenAI API key (use this OR ANTHROPIC_API_KEY OR OLLAMA_HOST) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (used if ANTHROPIC_API_KEY is set and OPENAI_API_KEY is not) · MCP_ALLOWED_ENTITIES=Comma-separated entity allowlist, enforced on JOINs too · MCP_BLOCKED_COLUMNS=Comma-separated column blocklist, stripped before the query is built · OPENAI_API_KEY=OpenAI (or OpenAI-compatible) API key 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key (web_search tool). Optional (v0.9). One of the AI answer-engines for ai_citation_track. · CF_API_TOKEN=Cloudflare API token. Optional; needed only for the Cloudflare tools. Scopes: Zone:Read, DNS:Read, Account Analytics:Read, and (only when destructive mode is on) Cache Purge:Purge, Single Redirect:Edit, Zone Settings:Edit, and (for bulk redirects) Account Rulesets:Edit + Account Filter Lists:Edit. · CF_ZONE=Default Cloudflare zone hostname, e.g. 'example.com'. · DATAFORSEO_LOGIN=DataForSEO Basic-auth login. Optional (v0.9). Unlocks SERP/PAA/related, keyword volume+difficulty+intent, competitor keyword-gap, and Google AI Overview citations for keyword_universe / serp_adjacency_expand / onpage_serp_gap auto-fetch / ai_citation_track. · DATAFORSEO_PASSWORD=DataForSEO Basic-auth password. Optional (v0.9). Required alongside DATAFORSEO_LOGIN. · GEMINI_API_KEY=Google Gemini API key (Search grounding). Optional (v0.9). One of the AI answer-engines for ai_citation_track. · GOOGLE_ADS_CUSTOMER_ID=Google Ads customer id (digits). Optional (v0.9). Required alongside GOOGLE_ADS_DEVELOPER_TOKEN. · GOOGLE_ADS_DEVELOPER_TOKEN=Google Ads API developer token. Optional (v0.9). Volume-only alternative to DataForSEO for keyword_universe; live use also needs an adwords-scope OAuth re-consent. · OPENAI_API_KEY=OpenAI API key (Responses web_search). Optional (v0.9). One of the AI answer-engines for ai_citation_track. · OPENPAGERANK_API_KEY=Open PageRank (DomCop) free API key. Optional (v0.9). Free competitor domain-authority proxy for onpage_serp_gap. · PERPLEXITY_API_KEY=Perplexity Sonar API key. Optional (v0.9). One of the AI answer-engines for ai_citation_track. · PSI_API_KEY=Google API key shared by PageSpeed Insights and Chrome UX Report History tools. Optional; both work anonymously at a tighter rate limit when unset. · SEO_MCP_ALLOW_DESTRUCTIVE=Set to 'true' to enable the Cloudflare cache-purge tools. Default false: all destructive tools refuse to run. · SEO_MCP_GA4_PROPERTY_ID=Default GA4 property, e.g. 'properties/123456789' or bare '123456789'. · SEO_MCP_GOOGLE_OAUTH_CLIENT=Path to your Desktop-app OAuth client-secrets JSON, downloaded from Google Cloud Console. Required for Search Console, Indexing, and GA4 tools. · SEO_MCP_GOOGLE_TOKEN=Writable path where the cached OAuth token is stored. On first use, a browser opens for one-time consent and the token is written here. Default: ${HOME}/.config/seo-monster/token.json · SEO_MCP_GSC_DEFAULT_SITE=Default Search Console property, e.g. 'sc-domain:example.com' or 'https://www.example.com/'. · SEO_MCP_INDEXNOW_KEY=IndexNow shared key (any 8-128 hex string you generate). Required only for the IndexNow tools. Host the key file at https://<your-host>/<key>.txt for engine verification. · SEO_MCP_INDEXNOW_KEY_LOCATION=Override the default IndexNow key-file URL (https://<host>/<key>.txt). Set only if you host the key file at a non-standard path. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI features (optional — free tier works without it) 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI trust scoring · GOOGLE_SAFE_BROWSING_API_KEY=Google Safe Browsing API key (free tier available). · GOOGLE_WEB_RISK_API_KEY=Google Web Risk API key (commercial). Degrades gracefully without it. 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI vision analysis 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI-assisted classification reasoning · HSPING_API_KEY=HSPing API key for official tariff schedule access 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI-powered fraud risk analysis · HMRC_CLIENT_ID=HMRC Developer Hub client ID for UK VAT validation · HMRC_CLIENT_SECRET=HMRC Developer Hub client secret for UK VAT validation 1 0.0 %
ANTHROPIC_API_KEY=Anthropic API key for AI-powered quantum triage analysis 1 0.0 %

Auf diesem Blatt stehen 50 von 7.577 Werten; sie decken 50 Einträge ab.

Blatt 15 von 152, 7.577 Werte insgesamt.

Gezählt wird die Projektion, dieselbe Tabelle, aus der die Liste filtert. Ein Eintrag zählt je Wert einmal.

tracevero · https://tracevero.de/werkzeuge/merkmal/mcp/roh_umgebungsbeschreibungen?seite=15